pfile->narrow_cset_desc = init_iconv_desc (pfile, ncset, SOURCE_CHARSET);
pfile->narrow_cset_desc.width = CPP_OPTION (pfile, char_precision);
+ pfile->utf8_cset_desc = init_iconv_desc (pfile, "UTF-8", SOURCE_CHARSET);
+ pfile->utf8_cset_desc.width = CPP_OPTION (pfile, char_precision);
pfile->char16_cset_desc = init_iconv_desc (pfile,
be ? "UTF-16BE" : "UTF-16LE",
SOURCE_CHARSET);
{
if (pfile->narrow_cset_desc.func == convert_using_iconv)
iconv_close (pfile->narrow_cset_desc.cd);
+ if (pfile->utf8_cset_desc.func == convert_using_iconv)
+ iconv_close (pfile->utf8_cset_desc.cd);
+ if (pfile->char16_cset_desc.func == convert_using_iconv)
+ iconv_close (pfile->char16_cset_desc.cd);
+ if (pfile->char32_cset_desc.func == convert_using_iconv)
+ iconv_close (pfile->char32_cset_desc.cd);
if (pfile->wide_cset_desc.func == convert_using_iconv)
iconv_close (pfile->wide_cset_desc.cd);
}
ISO/IEC 10646 is NNNNNNNN; the character designated by the
universal character name \uNNNN is that character whose character
short name in ISO/IEC 10646 is 0000NNNN. If the hexadecimal value
- for a universal character name is less than 0x20 or in the range
- 0x7F-0x9F (inclusive), or if the universal character name
- designates a character in the basic source character set, then the
- program is ill-formed.
+ for a universal character name corresponds to a surrogate code point
+ (in the range 0xD800-0xDFFF, inclusive), the program is ill-formed.
+ Additionally, if the hexadecimal value for a universal-character-name
+ outside a character or string literal corresponds to a control character
+ (in either of the ranges 0x00-0x1F or 0x7F-0x9F, both inclusive) or to a
+ character in the basic source character set, the program is ill-formed.
+
+ C99 6.4.3: A universal character name shall not specify a character
+ whose short identifier is less than 00A0 other than 0024 ($), 0040 (@),
+ or 0060 (`), nor one in the range D800 through DFFF inclusive.
*PSTR must be preceded by "\u" or "\U"; it is assumed that the
buffer end is delimited by a non-hex digit. Returns zero if the
(int) (str - base), base);
result = 1;
}
- /* The standard permits $, @ and ` to be specified as UCNs. We use
- hex escapes so that this also works with EBCDIC hosts. */
+ /* The C99 standard permits $, @ and ` to be specified as UCNs. We use
+ hex escapes so that this also works with EBCDIC hosts.
+ C++0x permits everything below 0xa0 within literals;
+ ucn_valid_in_identifier will complain about identifiers. */
else if ((result < 0xa0
+ && !CPP_OPTION (pfile, cplusplus)
&& (result != 0x24 && result != 0x40 && result != 0x60))
|| (result & 0x80000000)
|| (result >= 0xD800 && result <= 0xDFFF))
{
default:
return pfile->narrow_cset_desc;
+ case CPP_UTF8STRING:
+ return pfile->utf8_cset_desc;
case CPP_CHAR16:
case CPP_STRING16:
return pfile->char16_cset_desc;
for (i = 0; i < count; i++)
{
p = from[i].text;
- if (*p == 'L' || *p == 'u' || *p == 'U') p++;
+ if (*p == 'u')
+ {
+ if (*++p == '8')
+ p++;
+ }
+ else if (*p == 'L' || *p == 'U') p++;
+ if (*p == 'R')
+ {
+ const uchar *prefix;
+
+ /* Skip over 'R"'. */
+ p += 2;
+ prefix = p;
+ while (*p != '[')
+ p++;
+ p++;
+ limit = from[i].text + from[i].len;
+ if (limit >= p + (p - prefix) + 1)
+ limit -= (p - prefix) + 1;
+
+ for (;;)
+ {
+ base = p;
+ while (p < limit && (*p != '\\' || (p[1] != 'u' && p[1] != 'U')))
+ p++;
+ if (p > base)
+ {
+ /* We have a run of normal characters; these can be fed
+ directly to convert_cset. */
+ if (!APPLY_CONVERSION (cvt, base, p - base, &tbuf))
+ goto fail;
+ }
+ if (p == limit)
+ break;
+
+ p = convert_ucn (pfile, p + 1, limit, &tbuf, cvt);
+ }
+
+ continue;
+ }
+
p++; /* Skip leading quote. */
limit = from[i].text + from[i].len - 1; /* Skip trailing quote. */